SOTA Retrieval benchmarks and papers with code

Benchmarks

Dataset Name	SOTA Method	Metric
MS MARCO (dev)	ERNIE-Search	MRR@100.401	84	3d ago
Flickr2.4M (test)	QCQC (Blip2)	Ave Aes5.266	72	3d ago
MS-COCO	QCQC (Ours)	Ave Aes5.109	72	3d ago
TREC DL 2019	SPLADE-v3-DistilBERT	NDCG@1075.2	71	3d ago
Natural Questions (test)	CoopRAG	Top-5 Recall92.1	62	3d ago
MS MARCO v1	Double-encoder - Seismic (Half-precision)	Retrieval Latency (ms)0.5	57	3d ago
TREC-DL aggregate (test)		NDCG@1057.52	38	3d ago
Economic	Poi.-RAG	NDCG@250.242	35	3d ago
MLDR (test)	LMK	NDCG@1035	34	3d ago
QAMPARI N=1000 (test)	Retrieve-Verify-Retrieve (FT (Di) + FT (Dr))	MRecall@10033.7	27	3d ago
CommonsenseQA		Accuracy86.81	25	3d ago
ARC Challenge		Accuracy93.34	25	3d ago
BRIDGE (test)		Hit@1087	25	3d ago
HotpotQA	QRRanker-4B	R@596.9	24	3d ago
Caltech-UCSD Birds-200 (CUB) 2011 (test)	LFM+Ortho	MRR0.34	21	3d ago
STaRK PRIME Synthetic	mFAR	Recall@2068.3	20	3d ago
STaRK MAG Synthetic	FocusedR.	Recall@2078.8	20	3d ago
STaRK AMAZON Synthetic	AvaTaR	Recall@2060.57	20	3d ago
DiDeMo T+A -> V	PEAVL-OOD	Recall@182.1	20	2d ago
BRIGHT 12 datasets aggregate (test)	Contriever	NDCG@1012.74	20	3d ago
HotpotQA (test)	CoopRAG	Recall@288.8	20	3d ago
Entity Questions (test)	GAR best query	Top-100 Retrieval Accuracy91.8	20	3d ago
MS MARCO		Recall97.1	20	3d ago
HotpotQA full wiki (dev)	AISO	PEM88.17	19	3d ago
Clipper	QRhead+ReAttn	Recall@394	18	2d ago

Showing 25 of 251 rows

...